INDEX

Explanations

terms and concepts related to legal or formal documents and processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UNC

-0.15

Pru

-0.14

ona

-0.14

ioned

-0.14

enko

-0.14

typings

-0.14

olia

-0.14

_nat

-0.13

 åº

-0.13

POSITIVE LOGITS

precated

0.17

èĪ

0.15

agrams

0.15

0.14

fel

0.14

pto

0.14

ç½®

0.14

alach

0.14

taire

0.14

uilt

0.13

Activations Density 0.011%

terms and concepts related to legal or formal documents and processes

No Comments

No Known Activations